Hotel Lobby AI video for couples
She takes the left side, he takes the right and the spin at the eight-second mark. Their own faces and their own clothes, start to finish: no sunglasses or chains borrowed from the original.


Two photos, one orange booth. The Renoise Agent puts you both in the Hotel Lobby clip, rapping the original lines with the same moves, lip-synced to the original audio.
Opens in the Renoise Agent with your photos. It shows the credit cost before it generates.


Real output from two photos: the same 15 seconds, the original audio laid back on.
Real output at the default 480p, each from two photos. Turn the sound on: every clip carries the original audio.
She takes the left side, he takes the right and the spin at the eight-second mark. Their own faces and their own clothes, start to finish: no sunglasses or chains borrowed from the original.


Anyone can carry the verse. Here a grandmother keeps her glasses, silk scarf and camel coat through the whole routine, turn included.


Pets work too. The Agent first stands each one up in a plain outfit, then two cats point, spin and trade lines at the mic like the original pair.


What the Agent does with the original performance, and what you can still change.
The 15 seconds of the original track are laid back onto your clip, so it is ready to post as it is.
The point, the spin and the closing salute land on the same beats, with mouths on the lyrics.
Faces, hair and outfits come from your photos. The Agent checks no original performer slips in.
9:16, 720p, another model or matching outfits: say it in the prompt and the Agent prices it first.
Upload two photos — one of each person, or one photo with both of you in it — and the Renoise Agent remakes the Hotel Lobby clip with you in it: 15 seconds in the orange booth, the same gestures and spin, mouths on the lyrics, and the original audio on the result. The default is 16:9 at 480p and takes a few minutes.
Want it vertical for TikTok or sharper? Say so in the prompt; the Agent shows the price before it generates.
Want the whole story of the trend? Read the Migos AI video guide
Two photos and one request. The Agent handles the reference clip, the audio and the check at the end.
One clear, front-facing photo of each person, waist-up or full body. The first photo is the left side of the booth.
The default prompt makes the 16:9, 480p version. Add 9:16, 720p or an outfit change if you want one.
The Agent shows the credit cost, generates, lays the original audio back on and gives you the MP4.
All three copy the original moves; they differ in what you have to bring. Higgsfield figures are from higgsfield.ai/blog/higgsfield-genjutsu, accessed 9 November 2026; ours were measured the same day.
| What you get | Higgsfield Genjutsu Motion Transfer | Renoise face swap video | |
|---|---|---|---|
| What you upload | Two photos | A 4–30s source clip + up to 30 images | Your own clip (≤15s) + one face |
| Needs the original clip | — (built in) | ✓ | ✓ |
| Original audio on the result | ✓ | Not stated | — (silent) |
| Default output | 480p · 15s · 16:9 | Up to 1080p, source length | 480p · 4s |
| Entry cost | 180 credits a clip | 45 credits for 15s at 480p | 6 credits a second |
The Agent sends three things to [Wan 3.0](/models/wan-3) at 480p, the default tier: the original 15-second performance as the motion reference, its audio as the timing reference, and your two photos as the only source for faces and clothes. The model is told to copy the gestures, the spin and the mouth movement and to take nothing else from the performers in the clip. The result comes back silent and the original audio is laid back on, so the sound is the real track rather than a regenerated one.
Before it hands you the video, the Agent checks every few seconds that each face matches its photo and that neither original performer shows up — the turn around the eight-second mark is where a model is most likely to slip. If one does, it repairs once or tells you, rather than delivering it.
Use photos of yourself, or of people who agreed to be in the clip. Putting a stranger or a celebrity in the booth is still synthetic media about a real person, and the Agent will not make it with a child.
What happens to an upload on this page.
Picking a file only previews it on your device. Not one byte is stored until you sign in and click generate.
Uploads land in your private library, never a public gallery, and re-running the same photo stores nothing new.
Remove uploads and results from your library whenever you want.
As of October 2026, 100,000+ creators in 170+ countries and regions use Renoise AI, an AI video, image and audio platform, to generate 300,000+ images and videos with 30+ models.
Source: Renoise internal data, March–October 2026. Figures are rounded down and updated quarterly. Last updated
Real feedback from creators who use Renoise AI to make videos, images and ads.
Renoise is pretty easy to use, with a clean and smooth interface. The results from Seedance 2.5 also feel noticeably smoother in action sequences.
Renoise Ai is a good tool for making ai videos and photos. it puts several Ai models in one place, so you don't need to use many different apps.
あまりAIツールを使ったりしたことなかったですが、キャラクターの固定や動画を続いて作成できて使いやすいです。これからどんどん進んでいくアップデートが楽しみです。
Renoise has been a great platform for AI creativity. The tools are easy to use, the experience is smooth, and it makes creating content more enjoyable and efficient. I really appreciate the work the team is doing and look forward to seeing more improvements. Highly recommended!
What I like about Renoise AI compared to other platforms: Fast generation speed: Slow generation takes up way too much time, but Renoise AI is surprisingly about 30% faster. Intuitive and user-friendly UI: Cheaply made platforms have terrible UIs that make me not even want to log in, but Renoise is very clean and convenient. Remembers my previous settings: It helpfully remembers my last workspace settings. Some odd platforms force you to re-adjust everything every single time you generate a video, which is extremely frustrating. Overall preference: For all these reasons, Renoise AI is definitely my preferred platform. Thank you!
Renoise is your go to one stop all for ai creators. all view and use all models in one place, for any type of content you have your mind on!
I have a creat experience with the app. Consistent characters but also unique. THere were some issues with storyline continuity and non-typical humanoid characters.
One plan covers Wan 3.0, Seedance and every other model the Agent uses.
For your first AI creations
per month
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For your first AI creations
per month, billed annually
Save $48compared to monthly
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month, billed annually
Save $216compared to monthly
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month, billed annually
Save $960compared to monthly
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
Not on this page. A 15-second clip at 480p is 180 credits with Wan 3.0, and the Agent shows that price before it generates. Credits come with every plan and in top-up packs, and the same balance runs every other model on the account.
A TikTok trend from September 2026 that puts two people into a 2022 COLORS performance of the song "Hotel Lobby": an orange studio, one microphone hanging from the ceiling, two rappers trading lines. Creators swap themselves in with an AI video tool and post the result with the original sound.
Yes. The original 15 seconds of audio are laid back onto your clip after it is generated, and the mouths are timed to it, so you can post the MP4 as it is.
Not as a one-tap camera filter. Every version you see is an AI video made from photos. This page is that step: two photos in, the finished clip out.
Yes — this page is one. The original 15-second performance and its audio are built into the Renoise Agent’s Hotel Lobby skill, so you only bring two photos; the gestures, the spin and the timing come from the template.
Either works. Two front-facing photos, one per person, give the clearest faces; a single photo with both of you in it works too, and whoever is on the left of it takes the left side of the booth.
The clip is 15 seconds because that is the original verse the moves and the audio follow. HD, yes: 16:9 at 480p is only the default; ask for 720p (360 credits) or 9:16 in the prompt, and the Agent shows the price first.
Yes. Upload one clear photo of each pet. The Agent first makes a still of each one standing upright in a plain outfit, then uses those in the clip, so the pets take the performers’ places instead of sharing the booth with them.
No. Higgsfield Genjutsu copies the moves of a source clip you supply onto your photos. Here the original performance and its audio are built in, so the only things you bring are the two photos.
No. Failed and cancelled generations refund their credits automatically. The usual causes are a face the model cannot read — small, turned away or shadowed — or the content filter declining the photo itself.